Search Agent Capacity on Seal-0
53.4ScoreClaude-Sonnet-4.5
Evaluation results
| Method | Links | |
|---|---|---|
| Claude-Sonnet-4.52026.06 | 53.4 | |
| Seed2.0 Lite2026.06 | 52.3 | |
| GPT-5.2 High2026.06 | 51.4 | |
| Seed2.0 Pro2026.06 | 49.5 | |
| Claude-Opus-4.52026.06 | 47.7 | |
| Gemini-3-pro High2026.06 | 45.5 | |
| Gemini-3-Flash High2026.06 | 37.8 | |
| GPT-5-mini High2026.06 | 34.2 |